TensorFlow
End-to-end open source platform for machine learning, from research to production.
Overview
TensorFlow is an end-to-end open-source platform for machine learning, originally developed by Google's Machine Intelligence team (Google Brain) for internal ML research, and now maintained as a general-purpose framework used well beyond that original context. It provides stable Python and C++ APIs (with additional, non-guaranteed-stable APIs for other languages), and a broader ecosystem of tools, libraries, and community resources for both research and building/deploying ML-powered applications.
It's installed via pip (`tensorflow` for GPU-enabled builds on supported platforms, or `tensorflow-cpu` for a smaller CPU-only package), with GPU acceleration available through CUDA on Linux/Windows or device plugins for DirectX and Apple's Metal on other platforms.
TensorFlow fits teams and researchers building or deploying machine learning models who want a mature, widely adopted framework with first-class Python support and production deployment tooling, rather than a research-only or narrowly scoped ML library.
- Categories
- AI & Machine Learning
- Languages
- C++, Python
- License
- Apache-2.0
Related Projects
PyTorch
BSD-3-ClauseOpen source machine learning framework that accelerates the path from research prototyping to production deployment.
- AI & Machine Learning
Milvus
Apache-2.0Open source vector database built for scalable similarity search and AI applications.
- AI & Machine Learning
- Database
DeepSpeed
Apache-2.0Deep learning optimization library from Microsoft for training and running very large models efficiently across multiple GPUs.
- AI & Machine Learning
Ollama
MITRun large language models locally with a simple command-line interface and API.
- AI & Machine Learning
Spotted an error? Suggest an edit on GitHub.